# Mistral 7B Instruct v0.3 API prices

Mistral 7B Instruct v0.3 (mistral) — 127k context, 127k max output.
3 metered per-token offers from 5 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| OVHcloud AI Endpoints | $0.11 | $0.11 | — | 66k |
| Cortecs | $0.111 | $0.111 | — | 127k |
| Pioneer | $0.2 | $0.2 | $0.2 | 33k |

## Summary

- Cheapest input: $0.11 per 1M tokens (OVHcloud AI Endpoints)
- Cheapest output: $0.11 per 1M tokens (OVHcloud AI Endpoints)
- First-party: not listed separately
- Free offers: Nvidia
- Subscription plans (not per-token): none
- Released: 2025-04-01
- Inputs: text

HTML page: https://llmprice.gitlab.io/models/mistral-7b-instruct-v0-3/
Full dataset: https://llmprice.gitlab.io/data/catalog.json